A Metaheuristic-Driven Approach to Fine-Tune Deep Boltzmann Machines

01/14/2021
by   Leandro Aparecido Passos, et al.
0

Deep learning techniques, such as Deep Boltzmann Machines (DBMs), have received considerable attention over the past years due to the outstanding results concerning a variable range of domains. One of the main shortcomings of these techniques involves the choice of their hyperparameters, since they have a significant impact on the final results. This work addresses the issue of fine-tuning hyperparameters of Deep Boltzmann Machines using metaheuristic optimization techniques with different backgrounds, such as swarm intelligence, memory- and evolutionary-based approaches. Experiments conducted in three public datasets for binary image reconstruction showed that metaheuristic techniques can obtain reasonable results.

READ FULL TEXT

page 10

page 14

research
05/21/2018

Transductive Boltzmann Machines

We present transductive Boltzmann machines (TBMs), which firstly achieve...
research
11/14/2014

Deep Narrow Boltzmann Machines are Universal Approximators

We show that deep narrow Boltzmann machines are universal approximators ...
research
03/10/2023

Product Jacobi-Theta Boltzmann machines with score matching

The estimation of probability density functions is a non trivial task th...
research
12/10/2014

Quantum Deep Learning

In recent years, deep learning has had a profound impact on machine lear...
research
05/18/2018

DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors

Boltzmann machines are powerful distributions that have been shown to be...
research
07/03/2016

Robust Deep Appearance Models

This paper presents a novel Robust Deep Appearance Models to learn the n...
research
04/09/2018

A Generation Method of Immunological Memory in Clonal Selection Algorithm by using Restricted Boltzmann Machines

Recently, a high technique of image processing is required to extract th...

Please sign up or login with your details

Forgot password? Click here to reset